| From 01552bbaf7404514c31150137b03a1be45e36018 Mon Sep 17 00:00:00 2001 |
| From: Sasha Levin <sashal@kernel.org> |
| Date: Thu, 16 Apr 2020 16:46:10 -0700 |
| Subject: mm/mmap.c: Add cond_resched() for exit_mmap() CPU stalls |
| |
| From: Paul E. McKenney <paulmck@kernel.org> |
| |
| [ Upstream commit 0a3b3c253a1eb2c7fe7f34086d46660c909abeb3 ] |
| |
| A large process running on a heavily loaded system can encounter the |
| following RCU CPU stall warning: |
| |
| rcu: INFO: rcu_sched self-detected stall on CPU |
| rcu: 3-....: (20998 ticks this GP) idle=4ea/1/0x4000000000000002 softirq=556558/556558 fqs=5190 |
| (t=21013 jiffies g=1005461 q=132576) |
| NMI backtrace for cpu 3 |
| CPU: 3 PID: 501900 Comm: aio-free-ring-w Kdump: loaded Not tainted 5.2.9-108_fbk12_rc3_3858_gb83b75af7909 #1 |
| Hardware name: Wiwynn HoneyBadger/PantherPlus, BIOS HBM6.71 02/03/2016 |
| Call Trace: |
| <IRQ> |
| dump_stack+0x46/0x60 |
| nmi_cpu_backtrace.cold.3+0x13/0x50 |
| ? lapic_can_unplug_cpu.cold.27+0x34/0x34 |
| nmi_trigger_cpumask_backtrace+0xba/0xca |
| rcu_dump_cpu_stacks+0x99/0xc7 |
| rcu_sched_clock_irq.cold.87+0x1aa/0x397 |
| ? tick_sched_do_timer+0x60/0x60 |
| update_process_times+0x28/0x60 |
| tick_sched_timer+0x37/0x70 |
| __hrtimer_run_queues+0xfe/0x270 |
| hrtimer_interrupt+0xf4/0x210 |
| smp_apic_timer_interrupt+0x5e/0x120 |
| apic_timer_interrupt+0xf/0x20 |
| </IRQ> |
| RIP: 0010:kmem_cache_free+0x223/0x300 |
| Code: 88 00 00 00 0f 85 ca 00 00 00 41 8b 55 18 31 f6 f7 da 41 f6 45 0a 02 40 0f 94 c6 83 c6 05 9c 41 5e fa e8 a0 a7 01 00 41 56 9d <49> 8b 47 08 a8 03 0f 85 87 00 00 00 65 48 ff 08 e9 3d fe ff ff 65 |
| RSP: 0018:ffffc9000e8e3da8 EFLAGS: 00000206 ORIG_RAX: ffffffffffffff13 |
| RAX: 0000000000020000 RBX: ffff88861b9de960 RCX: 0000000000000030 |
| RDX: fffffffffffe41e8 RSI: 000060777fe3a100 RDI: 000000000001be18 |
| RBP: ffffea00186e7780 R08: ffffffffffffffff R09: ffffffffffffffff |
| R10: ffff88861b9dea28 R11: ffff88887ffde000 R12: ffffffff81230a1f |
| R13: ffff888854684dc0 R14: 0000000000000206 R15: ffff8888547dbc00 |
| ? remove_vma+0x4f/0x60 |
| remove_vma+0x4f/0x60 |
| exit_mmap+0xd6/0x160 |
| mmput+0x4a/0x110 |
| do_exit+0x278/0xae0 |
| ? syscall_trace_enter+0x1d3/0x2b0 |
| ? handle_mm_fault+0xaa/0x1c0 |
| do_group_exit+0x3a/0xa0 |
| __x64_sys_exit_group+0x14/0x20 |
| do_syscall_64+0x42/0x100 |
| entry_SYSCALL_64_after_hwframe+0x44/0xa9 |
| |
| And on a PREEMPT=n kernel, the "while (vma)" loop in exit_mmap() can run |
| for a very long time given a large process. This commit therefore adds |
| a cond_resched() to this loop, providing RCU any needed quiescent states. |
| |
| Cc: Andrew Morton <akpm@linux-foundation.org> |
| Cc: <linux-mm@kvack.org> |
| Reviewed-by: Shakeel Butt <shakeelb@google.com> |
| Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org> |
| Signed-off-by: Paul E. McKenney <paulmck@kernel.org> |
| Signed-off-by: Sasha Levin <sashal@kernel.org> |
| --- |
| mm/mmap.c | 1 + |
| 1 file changed, 1 insertion(+) |
| |
| diff --git a/mm/mmap.c b/mm/mmap.c |
| index bb1822ac99090..55bb456fd0d0f 100644 |
| --- a/mm/mmap.c |
| +++ b/mm/mmap.c |
| @@ -3171,6 +3171,7 @@ void exit_mmap(struct mm_struct *mm) |
| if (vma->vm_flags & VM_ACCOUNT) |
| nr_accounted += vma_pages(vma); |
| vma = remove_vma(vma); |
| + cond_resched(); |
| } |
| vm_unacct_memory(nr_accounted); |
| } |
| -- |
| 2.25.1 |
| |